{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 105,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 46.73658663770524,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 11.3797,
      "step": 1
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 44.523666214134316,
      "learning_rate": 9.090909090909091e-06,
      "loss": 11.5191,
      "step": 2
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 52.06639933238829,
      "learning_rate": 1.3636363636363637e-05,
      "loss": 10.8448,
      "step": 3
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 69.75134205890501,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 9.5655,
      "step": 4
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 50.314368468329306,
      "learning_rate": 2.272727272727273e-05,
      "loss": 4.1848,
      "step": 5
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 7.357015429387816,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 1.9862,
      "step": 6
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 7.401615020276034,
      "learning_rate": 3.181818181818182e-05,
      "loss": 1.9584,
      "step": 7
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 3.149164302427893,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 1.5975,
      "step": 8
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 1.9054072928164427,
      "learning_rate": 4.0909090909090915e-05,
      "loss": 1.4777,
      "step": 9
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 2.09522071898415,
      "learning_rate": 4.545454545454546e-05,
      "loss": 1.4076,
      "step": 10
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 1.4886426113733002,
      "learning_rate": 5e-05,
      "loss": 1.3226,
      "step": 11
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.594161802836668,
      "learning_rate": 4.946808510638298e-05,
      "loss": 1.2825,
      "step": 12
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 1.5132463664090081,
      "learning_rate": 4.893617021276596e-05,
      "loss": 1.3821,
      "step": 13
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.4916977417841104,
      "learning_rate": 4.840425531914894e-05,
      "loss": 1.2297,
      "step": 14
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.07234396111405,
      "learning_rate": 4.787234042553192e-05,
      "loss": 1.2448,
      "step": 15
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.9261313011360983,
      "learning_rate": 4.734042553191489e-05,
      "loss": 1.2062,
      "step": 16
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 1.3648296835839082,
      "learning_rate": 4.680851063829788e-05,
      "loss": 1.2428,
      "step": 17
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.9239559683166827,
      "learning_rate": 4.627659574468085e-05,
      "loss": 1.2616,
      "step": 18
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 0.7209850490291895,
      "learning_rate": 4.574468085106383e-05,
      "loss": 1.0656,
      "step": 19
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.9769698482701535,
      "learning_rate": 4.5212765957446815e-05,
      "loss": 1.0884,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6106942050998588,
      "learning_rate": 4.468085106382979e-05,
      "loss": 1.0672,
      "step": 21
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 0.801040183534444,
      "learning_rate": 4.414893617021277e-05,
      "loss": 1.0478,
      "step": 22
    },
    {
      "epoch": 1.0952380952380953,
      "grad_norm": 0.7146659615588544,
      "learning_rate": 4.3617021276595746e-05,
      "loss": 1.091,
      "step": 23
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.5905709163842993,
      "learning_rate": 4.3085106382978725e-05,
      "loss": 1.1275,
      "step": 24
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 0.5826060194579513,
      "learning_rate": 4.2553191489361704e-05,
      "loss": 1.0079,
      "step": 25
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 0.6151603075503278,
      "learning_rate": 4.2021276595744684e-05,
      "loss": 1.0802,
      "step": 26
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.5264186877249164,
      "learning_rate": 4.148936170212766e-05,
      "loss": 1.0406,
      "step": 27
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.5461664948214178,
      "learning_rate": 4.095744680851064e-05,
      "loss": 1.0072,
      "step": 28
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 0.4822129939360476,
      "learning_rate": 4.0425531914893614e-05,
      "loss": 1.0367,
      "step": 29
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.49848757883873196,
      "learning_rate": 3.9893617021276594e-05,
      "loss": 0.9754,
      "step": 30
    },
    {
      "epoch": 1.4761904761904763,
      "grad_norm": 0.5766625117987682,
      "learning_rate": 3.936170212765958e-05,
      "loss": 1.0631,
      "step": 31
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 0.4859811195017287,
      "learning_rate": 3.882978723404255e-05,
      "loss": 1.0003,
      "step": 32
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.5617547786833981,
      "learning_rate": 3.829787234042553e-05,
      "loss": 1.0312,
      "step": 33
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 0.4760704205398701,
      "learning_rate": 3.776595744680852e-05,
      "loss": 0.9957,
      "step": 34
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.5525097760212518,
      "learning_rate": 3.723404255319149e-05,
      "loss": 1.0427,
      "step": 35
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.48722284467868165,
      "learning_rate": 3.670212765957447e-05,
      "loss": 0.9141,
      "step": 36
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 0.48286908931413486,
      "learning_rate": 3.617021276595745e-05,
      "loss": 0.9701,
      "step": 37
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 0.509607069236827,
      "learning_rate": 3.563829787234043e-05,
      "loss": 0.9234,
      "step": 38
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.48664273824178367,
      "learning_rate": 3.5106382978723407e-05,
      "loss": 1.0605,
      "step": 39
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.4951502177756041,
      "learning_rate": 3.4574468085106386e-05,
      "loss": 1.0418,
      "step": 40
    },
    {
      "epoch": 1.9523809523809523,
      "grad_norm": 0.5599844810380401,
      "learning_rate": 3.4042553191489365e-05,
      "loss": 1.0207,
      "step": 41
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.47167217001219114,
      "learning_rate": 3.3510638297872344e-05,
      "loss": 0.8667,
      "step": 42
    },
    {
      "epoch": 2.0476190476190474,
      "grad_norm": 0.5766076030131434,
      "learning_rate": 3.2978723404255317e-05,
      "loss": 0.9305,
      "step": 43
    },
    {
      "epoch": 2.0952380952380953,
      "grad_norm": 0.5223243597728271,
      "learning_rate": 3.2446808510638296e-05,
      "loss": 0.8412,
      "step": 44
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.46907426786479,
      "learning_rate": 3.191489361702128e-05,
      "loss": 0.8973,
      "step": 45
    },
    {
      "epoch": 2.1904761904761907,
      "grad_norm": 0.4701126779049834,
      "learning_rate": 3.1382978723404254e-05,
      "loss": 0.8509,
      "step": 46
    },
    {
      "epoch": 2.238095238095238,
      "grad_norm": 0.48418735511330596,
      "learning_rate": 3.085106382978723e-05,
      "loss": 0.8757,
      "step": 47
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.6556800657324943,
      "learning_rate": 3.0319148936170216e-05,
      "loss": 0.9124,
      "step": 48
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.6014700280019579,
      "learning_rate": 2.9787234042553192e-05,
      "loss": 0.8755,
      "step": 49
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.5915165889418732,
      "learning_rate": 2.925531914893617e-05,
      "loss": 0.8925,
      "step": 50
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.6317703078383352,
      "learning_rate": 2.8723404255319154e-05,
      "loss": 0.8663,
      "step": 51
    },
    {
      "epoch": 2.4761904761904763,
      "grad_norm": 0.6429525648150871,
      "learning_rate": 2.819148936170213e-05,
      "loss": 0.8198,
      "step": 52
    },
    {
      "epoch": 2.5238095238095237,
      "grad_norm": 0.5187394614056622,
      "learning_rate": 2.765957446808511e-05,
      "loss": 0.7651,
      "step": 53
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.4845593782104512,
      "learning_rate": 2.7127659574468084e-05,
      "loss": 0.8805,
      "step": 54
    },
    {
      "epoch": 2.619047619047619,
      "grad_norm": 0.47561465960794413,
      "learning_rate": 2.6595744680851064e-05,
      "loss": 0.9561,
      "step": 55
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.48208401639762166,
      "learning_rate": 2.6063829787234046e-05,
      "loss": 0.8638,
      "step": 56
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 0.5193206572882076,
      "learning_rate": 2.5531914893617022e-05,
      "loss": 0.8062,
      "step": 57
    },
    {
      "epoch": 2.761904761904762,
      "grad_norm": 0.5299016279110512,
      "learning_rate": 2.5e-05,
      "loss": 0.8236,
      "step": 58
    },
    {
      "epoch": 2.8095238095238093,
      "grad_norm": 0.47247578172991544,
      "learning_rate": 2.446808510638298e-05,
      "loss": 0.786,
      "step": 59
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.4887209838922498,
      "learning_rate": 2.393617021276596e-05,
      "loss": 0.8275,
      "step": 60
    },
    {
      "epoch": 2.9047619047619047,
      "grad_norm": 0.47820835963456026,
      "learning_rate": 2.340425531914894e-05,
      "loss": 0.8581,
      "step": 61
    },
    {
      "epoch": 2.9523809523809526,
      "grad_norm": 0.46592054309550573,
      "learning_rate": 2.2872340425531915e-05,
      "loss": 0.8726,
      "step": 62
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.5063226147267863,
      "learning_rate": 2.2340425531914894e-05,
      "loss": 0.8522,
      "step": 63
    },
    {
      "epoch": 3.0476190476190474,
      "grad_norm": 0.4349456733161818,
      "learning_rate": 2.1808510638297873e-05,
      "loss": 0.7678,
      "step": 64
    },
    {
      "epoch": 3.0952380952380953,
      "grad_norm": 0.43322041549114737,
      "learning_rate": 2.1276595744680852e-05,
      "loss": 0.7291,
      "step": 65
    },
    {
      "epoch": 3.142857142857143,
      "grad_norm": 0.3891658154700991,
      "learning_rate": 2.074468085106383e-05,
      "loss": 0.7098,
      "step": 66
    },
    {
      "epoch": 3.1904761904761907,
      "grad_norm": 0.48090626334768466,
      "learning_rate": 2.0212765957446807e-05,
      "loss": 0.7075,
      "step": 67
    },
    {
      "epoch": 3.238095238095238,
      "grad_norm": 0.4192109123095055,
      "learning_rate": 1.968085106382979e-05,
      "loss": 0.7135,
      "step": 68
    },
    {
      "epoch": 3.2857142857142856,
      "grad_norm": 0.4538447830174013,
      "learning_rate": 1.9148936170212766e-05,
      "loss": 0.7293,
      "step": 69
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.400428247237971,
      "learning_rate": 1.8617021276595745e-05,
      "loss": 0.7182,
      "step": 70
    },
    {
      "epoch": 3.380952380952381,
      "grad_norm": 0.41259082028208505,
      "learning_rate": 1.8085106382978724e-05,
      "loss": 0.7111,
      "step": 71
    },
    {
      "epoch": 3.4285714285714284,
      "grad_norm": 0.42210992879504494,
      "learning_rate": 1.7553191489361703e-05,
      "loss": 0.7358,
      "step": 72
    },
    {
      "epoch": 3.4761904761904763,
      "grad_norm": 0.4805171232293903,
      "learning_rate": 1.7021276595744682e-05,
      "loss": 0.7693,
      "step": 73
    },
    {
      "epoch": 3.5238095238095237,
      "grad_norm": 0.4290739751199803,
      "learning_rate": 1.6489361702127658e-05,
      "loss": 0.7538,
      "step": 74
    },
    {
      "epoch": 3.571428571428571,
      "grad_norm": 0.46386967645771476,
      "learning_rate": 1.595744680851064e-05,
      "loss": 0.7483,
      "step": 75
    },
    {
      "epoch": 3.619047619047619,
      "grad_norm": 0.4600000815160992,
      "learning_rate": 1.5425531914893617e-05,
      "loss": 0.6961,
      "step": 76
    },
    {
      "epoch": 3.6666666666666665,
      "grad_norm": 0.48967690124437346,
      "learning_rate": 1.4893617021276596e-05,
      "loss": 0.7759,
      "step": 77
    },
    {
      "epoch": 3.7142857142857144,
      "grad_norm": 0.43799987175594934,
      "learning_rate": 1.4361702127659577e-05,
      "loss": 0.6973,
      "step": 78
    },
    {
      "epoch": 3.761904761904762,
      "grad_norm": 0.4170501746303817,
      "learning_rate": 1.3829787234042554e-05,
      "loss": 0.7713,
      "step": 79
    },
    {
      "epoch": 3.8095238095238093,
      "grad_norm": 0.44313691170789904,
      "learning_rate": 1.3297872340425532e-05,
      "loss": 0.7287,
      "step": 80
    },
    {
      "epoch": 3.857142857142857,
      "grad_norm": 0.3626173621626196,
      "learning_rate": 1.2765957446808511e-05,
      "loss": 0.7152,
      "step": 81
    },
    {
      "epoch": 3.9047619047619047,
      "grad_norm": 0.40980441661962524,
      "learning_rate": 1.223404255319149e-05,
      "loss": 0.7388,
      "step": 82
    },
    {
      "epoch": 3.9523809523809526,
      "grad_norm": 0.3476970829860624,
      "learning_rate": 1.170212765957447e-05,
      "loss": 0.6835,
      "step": 83
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.34534853622038764,
      "learning_rate": 1.1170212765957447e-05,
      "loss": 0.6936,
      "step": 84
    },
    {
      "epoch": 4.0476190476190474,
      "grad_norm": 0.34717149811141956,
      "learning_rate": 1.0638297872340426e-05,
      "loss": 0.6412,
      "step": 85
    },
    {
      "epoch": 4.095238095238095,
      "grad_norm": 0.39121639106624856,
      "learning_rate": 1.0106382978723404e-05,
      "loss": 0.6447,
      "step": 86
    },
    {
      "epoch": 4.142857142857143,
      "grad_norm": 0.3853359648131134,
      "learning_rate": 9.574468085106383e-06,
      "loss": 0.67,
      "step": 87
    },
    {
      "epoch": 4.190476190476191,
      "grad_norm": 0.333219732679469,
      "learning_rate": 9.042553191489362e-06,
      "loss": 0.6951,
      "step": 88
    },
    {
      "epoch": 4.238095238095238,
      "grad_norm": 0.4113440938373367,
      "learning_rate": 8.510638297872341e-06,
      "loss": 0.6427,
      "step": 89
    },
    {
      "epoch": 4.285714285714286,
      "grad_norm": 0.4292570295550588,
      "learning_rate": 7.97872340425532e-06,
      "loss": 0.6563,
      "step": 90
    },
    {
      "epoch": 4.333333333333333,
      "grad_norm": 0.3325469730092871,
      "learning_rate": 7.446808510638298e-06,
      "loss": 0.6215,
      "step": 91
    },
    {
      "epoch": 4.380952380952381,
      "grad_norm": 0.37390136106392785,
      "learning_rate": 6.914893617021277e-06,
      "loss": 0.6194,
      "step": 92
    },
    {
      "epoch": 4.428571428571429,
      "grad_norm": 0.4143640454410716,
      "learning_rate": 6.3829787234042555e-06,
      "loss": 0.6207,
      "step": 93
    },
    {
      "epoch": 4.476190476190476,
      "grad_norm": 0.3648244167487935,
      "learning_rate": 5.851063829787235e-06,
      "loss": 0.5998,
      "step": 94
    },
    {
      "epoch": 4.523809523809524,
      "grad_norm": 0.3512446333779434,
      "learning_rate": 5.319148936170213e-06,
      "loss": 0.6351,
      "step": 95
    },
    {
      "epoch": 4.571428571428571,
      "grad_norm": 0.339436273470992,
      "learning_rate": 4.787234042553191e-06,
      "loss": 0.599,
      "step": 96
    },
    {
      "epoch": 4.619047619047619,
      "grad_norm": 0.4440038854080703,
      "learning_rate": 4.255319148936171e-06,
      "loss": 0.584,
      "step": 97
    },
    {
      "epoch": 4.666666666666667,
      "grad_norm": 0.36581621694617583,
      "learning_rate": 3.723404255319149e-06,
      "loss": 0.6203,
      "step": 98
    },
    {
      "epoch": 4.714285714285714,
      "grad_norm": 0.3509331585886843,
      "learning_rate": 3.1914893617021277e-06,
      "loss": 0.5981,
      "step": 99
    },
    {
      "epoch": 4.761904761904762,
      "grad_norm": 0.3403976301106126,
      "learning_rate": 2.6595744680851065e-06,
      "loss": 0.6415,
      "step": 100
    },
    {
      "epoch": 4.809523809523809,
      "grad_norm": 0.30854856192103863,
      "learning_rate": 2.1276595744680853e-06,
      "loss": 0.6054,
      "step": 101
    },
    {
      "epoch": 4.857142857142857,
      "grad_norm": 0.2984920819758894,
      "learning_rate": 1.5957446808510639e-06,
      "loss": 0.6145,
      "step": 102
    },
    {
      "epoch": 4.904761904761905,
      "grad_norm": 0.30989076720361786,
      "learning_rate": 1.0638297872340427e-06,
      "loss": 0.6317,
      "step": 103
    },
    {
      "epoch": 4.9523809523809526,
      "grad_norm": 0.3438826262811614,
      "learning_rate": 5.319148936170213e-07,
      "loss": 0.6193,
      "step": 104
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.32644346890582215,
      "learning_rate": 0.0,
      "loss": 0.6277,
      "step": 105
    },
    {
      "epoch": 5.0,
      "step": 105,
      "total_flos": 8.363833783064986e+16,
      "train_loss": 1.3066247133981614,
      "train_runtime": 6202.6685,
      "train_samples_per_second": 0.266,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 1,
  "max_steps": 105,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.363833783064986e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}